AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation

Hanbo Bi, Yingchao Feng, Bowei Tong, Mengyu Wang, Haichen Yu, Yongqiang Mao, Hao Chang, Wenhui Diao, Peijin Wang, Yue Yu, Hanyang Peng, Yehong Zhang and 2 more

TPAMI 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 43 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add modal-specialized experts (ablation)RingMoE · NWPU-RESISC45 optical classificationaccuracy: 93.78 -> 95.05Improved
add modal-specialized experts (ablation)RingMoE · Dyna.-pla multi-spectral segmentationmIoU: 46.28 -> 47.60Improved
add collaborative experts (ablation)RingMoE · WHU-OPT-SAR multi-modal segmentationmIoU: 52.63 -> 54.70Improved
add shared expert (ablation)RingMoE · NWPU-RESISC45 optical classificationaccuracy: 94.59 -> 95.05Improved
add physics-informed SAR-L1 reconstruction loss instead of pixel-wise loss (ablation)RingMoE · SARSegL1mIoU: -5.67% mIoUImproved
add physics-informed SAR-L1 reconstruction loss instead of pixel-wise loss (ablation)RingMoE · SAR-AIRCraftmAP: -3.14% mAPImproved
scale backbone from 88M to 1B with RMoE layers (ablation)RingMoE · NWPU-RESISC45OA: 93.64 -> 95.90Improved
scale backbone from 88M to 1B with RMoE layers (ablation)RingMoE · AIDOA: 96.57 -> 98.19Improved
prune experts to top 25% instead of keeping all (ablation)RingMoE-Opt · NWPU-RESISC45accuracy: 95.90 -> 95.43No clear effect
use percentile top-25% pruning instead of fixed threshold 0.1 (ablation)RingMoE-Opt · NWPU-RESISC45accuracy: 95.06 -> 95.43Improved
retain more experts (top 75% instead of top 25%) (ablation)RingMoE-Opt · NWPU-RESISC45accuracy: 95.43 -> 95.71Improved
compress experts by SVD instead of summing weights into one FFN (ablation)RingMoE (1B) · NWPU-RESISC45OA: 94.81 -> 95.05Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy